An automatic detection of microcalcification in mammogram images using neuro-fuzzy classifier

Abstract

Breast cancer is a standout amongst the most widely recognised diseases and has a high rate of mortality around the world, significantly risking the health of the females. The presence of microcalcifications (MCs) is an imperative sign of early breast cancer. This study proposes an automatic technique for detecting the microcalcifications in mammogram images. The images are filtered using anisotropic diffusion filter, segmented using the technique based on cellular automata and finally classified into benign, malignant and normal using a neuro-fuzzy classifier. For extensive experimental analysis, mini-MIAS database is considered with sensitivity, specificity and accuracy as evaluation parameters. From qualitative and quantitative results, it is evident that the proposed classification method has achieved significant and improved performance compared to existing state-of-the-art classification technique like SVM, ANN, etc.